{"url":"/task/molecule-captioning","name":"Molecule Captioning","slug":"molecule-captioning","description_markdown":"Molecular description generation entails the creation of a detailed textual depiction illuminating the structure, properties, biological activity, and applications of a molecule based on its molecular descriptors. It furnishes chemists and biologists with a swift conduit to essential molecular information, thus efficiently guiding their research and experiments.","categories":[{"name":"Medical","url":"/area/medical"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":25,"papers_with_code":23,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/molecule-captioning-on-chebi-20","slug":"molecule-captioning-on-chebi-20","dataset":"ChEBI-20","dataset_url":"/dataset/chebi-20","rows_in_archive":33,"metrics":["BLEU-2","BLEU-4","METEOR","ROUGE-1","ROUGE-2","ROUGE-L","Text2Mol"],"first_row_in_archive_order":{"model":"Mol-LLM (Mistral-Instruct-v0.2)","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/molecule-captioning-on-l-m-24","slug":"molecule-captioning-on-l-m-24","dataset":"L+M-24","dataset_url":"/dataset/l-m-24","rows_in_archive":6,"metrics":["BLEU-2","BLEU-4","ROUGE-1","ROUGE-2","ROUGE-L","METEOR"],"first_row_in_archive_order":{"model":"Mol2Lang-VLM","paper_title":"Mol2Lang-VLM: Vision- and Text-Guided Generative Pre-trained Language Models for Advancing Molecule Captioning through Multimodal Fusion","paper_url":"/paper/mol2lang-vlm-vision-and-text-guided","paper_date":"2024-08-15","arxiv_id":null,"code_links":[{"title":"nhattruongpham/mol-lang-bridge","url":"https://github.com/nhattruongpham/mol-lang-bridge"}],"syntology":null}}],"datasets":[{"url":"/dataset/chebi-20","name":"ChEBI-20","full_name":"","num_papers_in_archive":43},{"url":"/dataset/l-m-24","name":"L+M-24","full_name":"","num_papers_in_archive":7}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":23,"of":23,"tagged_in_all":25,"items":[{"url":"/paper/a-molecular-multimodal-foundation-model","title":"A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language","date":"2022-09-12","arxiv_id":"2209.05481","repositories_listed":4,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":2}},{"url":"/paper/molfm-a-multimodal-molecular-foundation-model","title":"MolFM: A Multimodal Molecular Foundation Model","date":"2023-06-06","arxiv_id":"2307.09484","repositories_listed":2,"syntology":null},{"url":"/paper/xmolcap-advancing-molecular-captioning","title":"XMolCap: Advancing Molecular Captioning through Multimodal Fusion and Explainable Graph Neural Networks","date":"2025-05-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/automatic-annotation-augmentation-boosts","title":"Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language","date":"2025-02-10","arxiv_id":"2502.06634","repositories_listed":1,"syntology":null},{"url":"/paper/property-enhanced-instruction-tuning-for","title":"Property Enhanced Instruction Tuning for Multi-task Molecule Generation with Large Language Models","date":"2024-12-24","arxiv_id":"2412.18084","repositories_listed":1,"syntology":null},{"url":"/paper/geomclip-contrastive-geometry-text-pre","title":"GeomCLIP: Contrastive Geometry-Text Pre-training for Molecules","date":"2024-11-16","arxiv_id":"2411.10821","repositories_listed":1,"syntology":null},{"url":"/paper/vector-icl-in-context-learning-with","title":"Vector-ICL: In-context Learning with Continuous Vector Representations","date":"2024-10-08","arxiv_id":"2410.05629","repositories_listed":1,"syntology":null},{"url":"/paper/mol2lang-vlm-vision-and-text-guided","title":"Mol2Lang-VLM: Vision- and Text-Guided Generative Pre-trained Language Models for Advancing Molecule Captioning through Multimodal Fusion","date":"2024-08-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/3d-molt5-towards-unified-3d-molecule-text","title":"3D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modeling","date":"2024-06-09","arxiv_id":"2406.05797","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/reactxt-understanding-molecular-reaction-ship","title":"ReactXT: Understanding Molecular \"Reaction-ship\" via Reaction-Contextualized Molecule-Text Pretraining","date":"2024-05-23","arxiv_id":"2405.14225","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/atomas-hierarchical-alignment-on-molecule","title":"Atomas: Hierarchical Alignment on Molecule-Text for Unified Molecule Understanding and Generation","date":"2024-04-23","arxiv_id":"2404.16880","repositories_listed":1,"syntology":null},{"url":"/paper/biot5-towards-generalized-biological","title":"BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning","date":"2024-02-27","arxiv_id":"2402.17810","repositories_listed":1,"syntology":null},{"url":"/paper/towards-3d-molecule-text-interpretation-in","title":"Towards 3D Molecule-Text Interpretation in Language Models","date":"2024-01-25","arxiv_id":"2401.13923","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_unverified":2,"n_pointer_only":9}},{"url":"/paper/instructmol-multi-modal-integration-for","title":"InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery","date":"2023-11-27","arxiv_id":"2311.16208","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/molca-molecular-graph-language-modeling-with","title":"MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter","date":"2023-10-19","arxiv_id":"2310.12798","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_unverified":8,"n_pointer_only":16}},{"url":"/paper/biot5-enriching-cross-modal-integration-in","title":"BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations","date":"2023-10-11","arxiv_id":"2310.07276","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/from-artificially-real-to-real-leveraging","title":"From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery","date":"2023-09-11","arxiv_id":"2309.05203","repositories_listed":1,"syntology":null},{"url":"/paper/git-mol-a-multi-modal-large-language-model","title":"GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text","date":"2023-08-14","arxiv_id":"2308.06911","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/empowering-molecule-discovery-for-molecule","title":"Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective","date":"2023-06-11","arxiv_id":"2306.06615","repositories_listed":1,"syntology":null},{"url":"/paper/molxpt-wrapping-molecules-with-text-for","title":"MolXPT: Wrapping Molecules with Text for Generative Pre-training","date":"2023-05-18","arxiv_id":"2305.10688","repositories_listed":1,"syntology":null},{"url":"/paper/unifying-molecular-and-textual","title":"Unifying Molecular and Textual Representations via Multi-task Language Modelling","date":"2023-01-29","arxiv_id":"2301.12586","repositories_listed":1,"syntology":null},{"url":"/paper/graph-based-molecular-representation-learning","title":"Graph-based Molecular Representation Learning","date":"2022-07-08","arxiv_id":"2207.04869","repositories_listed":1,"syntology":null},{"url":"/paper/translation-between-molecules-and-natural","title":"Translation between Molecules and Natural Language","date":"2022-04-25","arxiv_id":"2204.11817","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}